Skip to main content
SpringerLink
Log in

Flaws in evaluation schemes for pair-input computational predictions

  • Correspondence
  • Published:

From Nature Methods

View current issue Submit your manuscript

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1: Toy example (nine proteins) demonstrating prediction of protein-protein interactions and showing the shortcomings of a typical cross-validation scheme.

References

  1. Shen, J. et al. Proc. Natl. Acad. Sci. USA 104, 4337–4341 (2007).

    Article  CAS  Google Scholar 

  2. Wikberg, J.E. & Mutulis, F. Nat. Rev. Drug Discov. 7, 307–323 (2008).

    Article  CAS  Google Scholar 

  3. Yabuuchi, H. et al. Mol. Syst. Biol. 7, 472 (2011).

    Article  CAS  Google Scholar 

  4. Bellucci, M., Agostini, F., Masin, M. & Tartaglia, G.G. Nat. Methods 8, 444–445 (2011).

    Article  CAS  Google Scholar 

  5. Gottlieb, A., Stein, G.Y., Ruppin, E. & Sharan, R. Mol. Syst. Biol. 7, 496 (2011).

    Article  Google Scholar 

  6. Vert, J.-P. & Yamanishi, Y. Advances in Neural Information Processing Systems vol. 17 (eds. Saul, L., Weiss. Y. & Bottou, L.) 1433–1440 (MIT Press, Cambridge, Massachusetts, USA, 2005).

    Google Scholar 

  7. Flicek, P. et al. Nucleic Acids Res. 39, D800–D806 (2011).

    Article  CAS  Google Scholar 

  8. Schaefer, M.H. et al. PLoS ONE 7, e31826 (2012).

    Article  CAS  Google Scholar 

  9. Tropsha, A. & Golbraikh, A. Curr. Pharm. Des. 13, 3494–3504 (2007).

    Article  CAS  Google Scholar 

  10. Olah, M., Bologa, C. & Oprea, T.I. J. Comput. Aided Mol. Des. 18, 437–449 (2004).

    Article  CAS  Google Scholar 

Download references

Acknowledgements

We thank W.S. Noble, A. Ben-Hur, J.-P. Vert and V. Helms for stimulating discussions and critical comments on the manuscript. This work was supported by grants to E.M.M. from the US National Institutes of Health, the US Army (58343-MA), Cancer Prevention and Research in Texas and the Welch (F1515) Foundation. Y.P. acknowledges financial support from the Deutsche Forschungsgemeinschaft (DFG-Forschungsstipendium).

Author information

Authors and Affiliations

  1. Center for Systems and Synthetic Biology, Institute for Cellular and Molecular Biology, University of Texas at Austin, Austin, Texas, USA

    Yungki Park & Edward M Marcotte

Authors
  1. Yungki Park
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Edward M Marcotte
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Yungki Park or Edward M Marcotte.

Ethics declarations

Competing interests

The authors declare no competing financial interests.

Supplementary information

Supplementary Text and Figures

Supplementary Tables 1–4, Supplementary Methods and Supplementary Discussion (PDF 534 kb)

Rights and permissions

Reprints and permissions

About this article

Cite this article

Park, Y., Marcotte, E. Flaws in evaluation schemes for pair-input computational predictions. Nat Methods 9, 1134–1136 (2012). https://doi.org/10.1038/nmeth.2259

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/nmeth.2259

  • Springer Nature America, Inc.

This article is cited by

Search

Navigation